Presentation is loading. Please wait.

Presentation is loading. Please wait.

Horst Fischer University Freiburg / CERN COMPASS Computing.

Similar presentations


Presentation on theme: "Horst Fischer University Freiburg / CERN COMPASS Computing."— Presentation transcript:

1 Horst Fischer University Freiburg / CERN COMPASS Computing

2 Outline Central Data Recording and Event Database Event Reconstruction Some words on statistics Analysis Model A word of warning: 2001  COMPASS Detector commissioning 2002  COMPASS Analysis commissioning Hence, some numbers are preliminary and not yet on rock solid ground

3 35 MB/s input rate Central Data Recording Data servers: Up to 20 x 500GB During shutdown: Use disk of online farm as additional stage pool (additional 3.5 TB) CASTOR: CERN development of a “infinite file system” COMPASS is the first experiment which uses CASTOR heavily DST production tape

4 Central Data Recording Design value (35MB/s) 260 TByte in ~100 days Compare to BaBar: 1TByte/day 662 TByte in 1999-2002 Or CDF: 500 TByte/year (U.S. year >> 100 days) May 27Sep 18 GB

5 Data in Database 2001: Detector commissioning:65 days, 13 TByte Target polarized longitudinally:14 days, 15 TByte total: 28 TByte 2002: Target polarized longitudinally:57 days, 173k spills Target polarized transversely:19 days, 52k spills total: 260 TByte 2002 on average 22k triggers/spill  5 Gev (3.8Gev, 1.2Gev) online: ~260,000 files (~80 files / run) Objectivity faced out at CERN and replaced by Oracle9i After transfer to CCF ~2000ev/s are formatted into Objectivity/DB Different data bases for raw events and special events  Planed: event reconstruction before storing DB federations to tape  2002: offline reconstruction (calibrations were/are not available)

6 Database Migration  Raw events Original DATE format, flat files kept in Castor  Metadata Mainly event headers and navigational information for raw and reconstructed events in relational database 0.25% of the raw data volume at CERN stored in Oracle (but without Oracle-specific features) Possibility for another database in the outside institutes (MySQL)  Conditions data Migrated to the new CDB implementation based on Oracle No interface change (abstract interface)  DST Object streaming to files

7 More on DB Migration  CERN IT/DB is involved in the migration project to a large extent Planning activities started early this year Several people (IT/DB/PDM section) working on the project Coordinating experiments and with other IT groups –Servers: ADC group –Castor: DS group Migrate database to “borrowed” tapes  COMPASS IT/DB is working closely with COMPASS experts Certify interfaces to Oracle DB  Licenses being negotiated between CERN and Oracle for >2003

8 Event Reconstruction Compass Computing Farm:  100 dual Processor PIII Linux PCs  Mainly for event reconstruction and (Mini)-DST production  maintained and operated by CERN staff  Part of CERN LSF BATCH-system Average time to reconstruct one event: 400ms/ev (300…500 ms, during the first 400ms of a spill up to 1300ms/ev) 5Gev * 400ms/ev = 2Gs / 200CPUs = 10 Ms/CPU at 100% efficiency: = 115 days on 200 CPUs Today: about 30% of 2002 data are being pre-processed for preliminary physics analysis (since September) Process as much in parallel as possible: 1 run : ~ 80 data files : ~ 80 batch jobs running at the same time

9 Batch Statistics Jobs per week It’s a full time job to control data flow and quality of output Must set-up production shifts to share work load like one does for data taking Alternative: Outsourcing = hire technicians? CPU time per week

10 COMPASS Analysis Model Calibrations MySQL DST Oracle 9i mini DST ROOT tree RAW data Oracle 9i CORAL PHAST micro DST ROOT tree micro DST ROOT tree micro DST ROOT tree Conditions PVSS/Oracle 9i e-Logbook MySQL

11 CORAL - Event Reconstruction = CO MPASS R econstruction and A na L ysis Program  Modular architecture  Following OO techniques  Fully written in C++  Written from scratch  Defined interfaces for easy exchange of external packages (e.g. OB/DB  Oracle9i  Access to event, conditions and calibration data bases  Not as user friendly, however, as it may look

12 Calibrations etc. Presently (2001 & 2002): Calibration DB: 42 MByte Map DB: 4.5 MByte Geometry DB:4.4 MByte Calibrations stored in Run dependent file structured data base which allows for different versions Bookkeeping: MySQL (project launched recently) Calibrations: Alignment (Torino) RICH refraction index, PID likelihood (Trieste) Time-zero calibrations (Bonn, Erlangen & Mainz) r-t relations (Saclay & Munich) Amplitude and time for GEM & Silicon (Munich) Calorimeter (Dubna & Protvino) Detector calibrations can not be automated yet. Still everyday new surprises …  Is a drain for our most valuable resource “manpower”  Tasks must stay in responsibility of the listed groups, otherwise very inefficient because of learning curve

13 Experience: Reconstruction & Analysis (my personal, subjective, view)  “Distributed” data analysis is very inefficient (presently!)  Size of individual groups participating in analysis is not yet large enough to make fast & significant progress by their own Frequently struggling with infrastructural problems Communication between satellites is poor or not existing Missing discussions & stimulations  This unsatisfactory situation may improve with time (?)  COMPASS needs a strong & centralized analysis group  Exchange with satellite groups due to travel of people coming/leaving from/to home institutes Short term SOLUTION:

14 Analysis: Where & Resources significant core of experts @ CERN “Analysis Center” Resources: CCF+… Trieste (55 GHz, 4 TB) TU Munich (26 GHz, 2.4TB) 2003: double GridKa (German LHC Tier 1) 530 GHz, 50TB COMPASS: 20 GHz 2003: double Freiburg (40 GHz, 3TB) 2003: * 1.5 Dubna (14.5 GHz,1.7TB) 2003: double Saclay (  Lyon) Mainz/Bonn Torino (66 GHz, 1 TB)

15 Conclusions & Suggestions COMPASS faces its first year of “real” data analysis Challenges are enormous: calibrations, data handling, etc. … but very interesting physics ahead and thus its worth all the efforts ( and sleepless nights) Unfortunately we are forced to change event data base in a moment when we should work with full pace on our first data analysis (disadvantage when you are dependent on third party decisions!) Tools for event reconstruction and (Mini- & Micro-) DST analysis exist but need continuous improvements and adaptations to reality Still weak on tools to submit & monitor and manipulate & handle output of 200+ batch jobs per hour (effort was underestimated by many of us) Presently under evaluation: ALIEN (ALICE development) Organizational structure of analysis group: 1. Establish a strong core group at CERN with regular WORK(!)shops 2. Setup shifts for DST production


Download ppt "Horst Fischer University Freiburg / CERN COMPASS Computing."

Similar presentations


Ads by Google